# An Efficient Deep Template Matching and In-Plane Pose Estimation Method via Template-Aware Dynamic Convolution

arXiv: https://arxiv.org/abs/2510.01678 · HTML: https://mlsanity.com/paper/2510.01678/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 34 references that are in the map.
- First posted on arXiv 2 Oct 2025.

## Builds on (most cited first, 10 of 10)

- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [R2D2: Repeatable and Reliable Detector and Descriptor](https://mlsanity.com/paper/1906.06195/) (2019)
- [QATM: Quality-Aware Template Matching For Deep Learning](https://mlsanity.com/paper/1903.07254/) (2019)
- [Learning Accurate Template Matching with Differentiable Coarse-to-Fine Correspondence Refinement](https://mlsanity.com/paper/2303.08438/) (2023)
- [Fast Normalized Cross-Correlation for Template Matching with Rotations](https://mlsanity.com/paper/2311.07561/) (2023)
- [Hard-normal Example-aware Template Mutual Matching for Industrial Anomaly Detection](https://mlsanity.com/paper/2303.16191/) (2023)
- [Efficient High-Resolution Template Matching with Vector Quantized Nearest Neighbour Fields](https://mlsanity.com/paper/2306.15010/) (2023)
- [Tensorial template matching for fast cross-correlation with rotations and its application for tomography](https://mlsanity.com/paper/2408.02398/) (2024)
- [Template Matching in Images using Segmented Normalized Cross-Correlation](https://mlsanity.com/paper/2502.01286/) (2025)

## Abstract (arXiv)

In industrial inspection and component alignment tasks, template matching requires efficient estimation of a target's position and geometric state (rotation and scaling) under complex backgrounds to support precise downstream operations. Traditional methods rely on exhaustive enumeration of angles and scales, leading to low efficiency under compound transformations. Meanwhile, most deep learning-based approaches only estimate similarity scores without explicitly modeling geometric pose, making them inadequate for real-world deployment. To overcome these limitations, we propose a lightweight end-to-end framework that reformulates template matching as joint localization and geometric regression, outputting the center coordinates, rotation angle, and independent horizontal and vertical scales. A Template-Aware Dynamic Convolution Module (TDCM) dynamically injects template features at inference to guide generalizable matching. The compact network integrates depthwise separable convolutions and pixel shuffle for efficient matching. To enable geometric-annotation-free training, we introduce a rotation-shear-based augmentation strategy with structure-aware pseudo labels. A lightweight refinement module further improves angle and scale precision via local optimization. Experiments show our 3.07M model achieves high precision and 14ms inference under compound transformations. It also demonstrates strong robustness in small-template and multi-object scenarios, making it highly suitable for deployment in real-time industrial applications. The code is available at:https://github.com/ZhouJ6610/PoseMatch-TDCM.